One-click install
npx skills add https://github.com/buzzbysolcex/buzz-bd-agent --skill clawrouter-buzzbysolcex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clawrouter
Source: https://github.com/buzzbysolcex/buzz-bd-agent/tree/main/skills
Command: npx skills add https://github.com/buzzbysolcex/buzz-bd-agent --skill clawrouter-buzzbysolcex

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ClawRouter eliminates unnecessary LLM spend by automatically routing each task to the lowest-cost model that can still handle it well.

Core Features & Use Cases

  • Cost-aware model selection: Sends simple tasks (token scanning, data fetching, summaries, health checks) to FREE models first, and complex reasoning (scoring, outreach drafting) to MiniMax.
  • Deterministic routing rules: Uses explicit “FREE-first” and “PAID-for-complex” policies to keep outcomes consistent while controlling cost.
  • Failure fallback behavior: If a FREE model fails, it automatically falls back to MiniMax.
  • Sub-agent constraint handling: Accounts for the limitation that sub-agents cannot yet use FREE models, keeping their tasks concise.

Quick Start

Use ClawRouter to perform a token data fetch by first selecting a free model and returning results efficiently without paying for complex reasoning.

Frequently Asked Questions about clawrouter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reduce LLM inference costs by routing simple tasks to free models?

LLM cost optimization routes simple tasks like token scanning and data fetching to FREE models first, reserving paid models like MiniMax for complex reasoning such as BD scoring and outreach drafting to minimize spend.

What is the best way to set up fallback strategies when a free LLM API call fails?

The best fallback strategy automatically reroutes the request to a paid model like MiniMax if a FREE model call fails, ensuring task completion while maintaining deterministic routing rules for cost control.

Can I use cost-aware model selection for token scanning and market data aggregation?

Yes, cost-aware model selection supports token scanning, market data aggregation, API fetching, and simple formatting by directing these lightweight tasks to FREE tiers to preserve answer quality while eliminating unnecessary spend.

Does LLM routing work with sub-agents that cannot access free model tiers?

LLM routing accounts for sub-agent limitations by keeping their tasks concise since sub-agents cannot yet use FREE models, requiring routing rules to manage model switches and enforce fallback behavior for complex reasoning.

How do I enforce deterministic routing rules for task dispatch across multiple LLM providers?

You can enforce deterministic routing rules by applying explicit FREE-first and PAID-for-complex policies, issuing model switches via the /model command, and tracking routing decisions to keep outcomes consistent while controlling cost.